Online Associative Multi-Stage Goal Babbling Toward Versatile Learning of Sensorimotor Skills

We develop an online learning scheme inspired by the versatility of the human learning system to bootstrap several sensorimotor skills in “Learning while Behaving” fashion. Our proposed scheme is able to represent multiple coordination styles to handle assigned tasks flexibly. We have four main contributions in this paper. First, we propose a novel online learning scheme to learn several robot models simultaneously, online, from scratch and in a plain exploratory fashion. Second, we develop an incremental online associative radial basis function network which is constructed from scratch to solve the learned mapping ambiguities, e.g., redundancy, dynamically based on the current robot state. Third, we combine both proposed schemes to inherit their advantages in Associative Multi-Stage Goal Babbling. Fourth, we propose a parameter-sharing technique to increase efficiency and speed up the online learning process. All the proposed methods are evaluated in different illustrative experiments. They demonstrate promising performance with sufficient accuracy and a reasonable number of samples.